© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 30504
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly in a political or social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    691
    +0.12
    0.6%
    506
    +0.12
    0.6%
    190
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.12
    0.01
    440
    +0.12
    0.08
    572
    +0.10
    0.09
    Negative Logits
     Paragu
    -0.88
    Unity
    -0.83
    oÄŁ
    -0.83
    agos
    -0.81
    unity
    -0.79
     Okin
    -0.78
     Xan
    -0.78
    Ky
    -0.77
     Hond
    -0.77
     Kasich
    -0.77
    POSITIVE LOGITS
     Smith
    2.64
    Smith
    2.52
    smith
    1.59
     Sm
    1.33
     SM
    1.28
    mith
    1.22
     sm
    1.17
    SM
    1.10
     Weber
    1.09
    Sm
    1.08
    Activations Density 4.931%

    No Known Activations